Generating Diverse Code Explanations using the GPT-3 Large Language Model

By Stephen MacNeil, Andrew Tran, Dan Mogil, Seth Bernstein, Erin Ross, Ziheng Huang. 2022

200 citations recorded by the source corpus.

Good explanations are essential to efficiently learning introductory programming concepts [10]. To provide high-quality explanations at scale, numerous systems automate the process by tracing the execution of code [8, 12], defining terms [9], giving hints [16], and providing error-specific feedback [10, 16]. However, these approaches often require manual effort to configure and only explain a single aspect of a given code segment. Large language models (LLMs) are also changing how students interact with code [7]. For example, Github's Copilot can generate code for programmers [4], leading researchers to raise concerns about cheating [7]. Instead, our work focuses on LLMs' potential to support learning by explaining numerous aspects of a given code snippet. This poster features a systematic analysis of the diverse natural language explanations that GPT-3 can generate automatically for a given code snippet. We present a subset of three use cases from our evolving design space of AI Explanations of Code.

Subfields: Computer Science Applications, Hardware and Architecture, Software, Large Language Models, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Science Applications

In Software

In Large Language Models

In Code Generation & Program Synthesis

Citations in the corpus

Comparing Code Explanations Created by Students and Large Language Models (2023, background): “creation by humans) learning materials [11, 38], including code explanations [26, 27].”
Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book (2022, methodology): “In computer science classrooms, LLMs are beginning to be used to generate assignments [36], help students to write their code [3, 40], and to generate explanations of code snippets to facilitate learning [23].”
ChatGPT and large language models in academia: opportunities and challenges (2023, background): “LLMs provide benefits and opportunities in education for students by assisting with research and academic writing [15] or using them as an interactive study guide which may include generating practice exams and being provided immediate feedback [16, 17].”
Using Large Language Models to Enhance Programming Error Messages (2022, background): “Tools like Codex are able to generate new programming assignments [36] and code explanations [29] when provided examples.”